The value of Radiomics combined with Machine Learning in the staging of liver Fibrosis
Fengxian Fan1, Weiting Huang2, Yanli Jiang1, Wanjun Hu1, Jing Zhang1, and Jialiang Ren3
1LanZhou University Second Hospital, LanZhou, China, 2LanZhou University, LanZhou, China, 3GE Healthcare, Shanghai, China
In this study, 244 people had liver pathologic and MRI were divided into training and testing cohorts to developed and validated radiomics models for differentiation of low(0-2) from high(3-4) stage fibrosis. The results showed radiomics models of T1WI had a powerful ability to stage fibrosis.
Figure 2. a. ROC curve analysis of radiomics models in the testing cohort (AUC=0.85). b. ROC curve analysis of Fibroscan(AUC=0.83), APRI(AUC=0.68), FIB-4(AUC=0.69).
Table 1.The eighteen valuable features.